军事知识服务平台
面向动力煤分选过程的多智能体协同优化决策方法研究
Study on a multi-agent collaborative optimization decision-making method for the thermal coal preparation process
摘要 为解决动力煤分选过程中脱粉粒度固定、"预先脱粉+重介质分选"工序独立调控、煤质波动下难以实现效益最优等问题,提出一种基于多智能体深度强化学习的协同优化决策方法,将原煤脱粉与重介质分选两个关键环节抽象为协作智能体,设计兼顾经济效益与产品质量的团队奖励函数,引入注意力机制优化策略网络,构建数字孪生仿真环境,依托集中式训练分布式执行框架完成智能体协同训练与仿真测试.为验证该策略方法的优越性,设置固定参数策略与单智能体独立控制策略开展对比分析.结果表明:在典型煤质波动工况下,该策略方法累计经济效益提升 5.6%以上,精煤灰分合格率可达 99.8%,分选密度波动均值为 0.004 g/cm3;面对煤质突变的极端工况,仍可维持正向经济效益增长,在细粒级含量>50%的恶劣工况下经济效益仍可提升 1.5%.该方法可打破选煤系统单环节局部优化局限,实现原煤脱粉与重介质分选跨工序协同调控,为选煤智能化由"感知—控制"迈向"认知—决策"提供理论与方法支撑.
Abstract:
To address the problems of a fixed desliming particle size,independent control of the"pre-deslim-ing+dense-medium separation"processes,and the difficulty in achieving optimal economic benefits under fluc-tuating coal quality during thermal coal preparation,a multi-agent deep reinforcement learning-based collaborat-ive optimization decision-making method is proposed.The raw coal desliming and dense-medium separation processes are modeled as two cooperative agents,and a team reward function that considers both economic be-nefits and product quality is designed.An attention mechanism is introduced to optimize the policy network,and a digital twin-based simulation environment is developed.Based on the Centralized Training with Decentralized Execution framework,collaborative training and simulation testing of the agents are conducted.To verify the su-periority of this strategy,comparative analyses were performed against a fixed-parameter strategy and an inde-pendent single-agent control strategy.The results show that under typical coal quality fluctuation conditions,this strategy increases cumulative economic benefits by more than 5.6%,achieves a clean coal ash content qualifica-tion rate of up to 99.8%,and maintains an average fluctuation in separation density of 0.004 g/cm3.Under ex-treme conditions involving abrupt changes in coal quality,the strategy still maintains positive economic growth.Even under severe conditions where the fine-particle content exceeds 50%,economic benefits can still be im-proved by 1.5%.The proposed method overcomes the limitations of local optimization at individual stages of the coal preparation system and enables cross-process collaborative control of raw coal desliming and dense-medi-um separation,providing theoretical and methodological support for the transformation of coal preparation intel-ligence from"perception-control"toward"cognition-decision-making."